arXiv AI
HumanoidNDM: Closing the Training-Deployment Gap of Motion Tracking via Humanoid Neural Dynamics Model
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
arXiv Machine Learning
Jun 9
Mind Your Steps: A General Learning Framework for Accurate Humanoid Foothold Tracking
arXiv:2606. 08253v1 Announce Type: cross Abstract: Enabling humanoid robots to operate in complex, dynamic environments remains a critical challenge, fundamentally limited by the ability to navigate robustly, safely, and accurately.
arXiv Computer Vision
Sep 21
ULTRA: Unified Multimodal Control for Autonomous Humanoid Whole-Body Loco-Manipulation
ULTRA is a unified framework for autonomous humanoid whole-body locomotion and manipulation that overcomes limitations of prior methods by combining a physics-driven neural retargeting algorithm with a multimodal controller. The retargeting algorithm translates large-scale motion capture data into physically plausible humanoid motions, while the controller learns to handle both dense motion references and sparse task specifications using a range of sensory inputs, from accurate motion-capture states to noisy egocentric vision. In simulation and on a real Unitree G1 humanoid, ULTRA demonstrates improved generalization and robustness, enabling coordinated whole-body behavior from sparse intent without relying on test-time reference motions.
arXiv AI
Jul 2
KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills
arXiv:2506. 12851v3 Announce Type: replace-cross Abstract: Humanoid robots are promising to acquire various skills by imitating human behaviors.
arXiv AI
Jun 17
Any2Any: Efficient Cross-Embodiment Transfer for Humanoid Whole-Body Tracking
arXiv:2605. 23733v2 Announce Type: replace-cross Abstract: Whole-body tracking (WBT) models have become a key foundation for humanoid robots, enabling them to imitate diverse motions with high fidelity.
arXiv Computer Vision
Oct 26
ViT-H: Generative Video-To-Humanoid Control with Motion Tracking Feedback
ViT-H is a video‑to‑humanoid control framework that generates humanoid reference motions directly from monocular human videos using a diffusion model, eliminating the need for separate reconstruction, retargeting, and tracking stages. The system incorporates motion‑tracking feedback to fine‑tune the generator via preference optimization, and an autoregressive variant enables real‑time teleoperation with sub‑400 ms latency. Experiments on the Unitree G1 robot show that ViT‑H surpasses existing reconstruction‑retargeting‑tracking pipelines in motion quality and executability, and its performance scales positively with model size and data volume.
arXiv AI
Sep 1
PhyGile: Physics-Prefix Guided Motion Generation for Agile General Humanoid Motion Tracking
arXiv:2603.19305v3 Announce Type: replace-cross Abstract: Humanoid robots are expected to execute agile and expressive whole-body motions in real-world settings. Existing text-to-motion generation mo...